# library(shiny)
library(dplyr)
library(ggplot2)
library(tidyr)
library(reshape2) # reshaping the data
library(corrplot) # correlation matrix
library(car) # applied regression
data_1 <- read.csv(file = "./salary_data_cleaned.csv") #
data_2 <- read.csv(file = "./glassdoor_jobs.csv") #
data_3 <- read.csv(file = "./eda_data.csv") # data science job postings from Glassdoor.com for 2017-2018 33 variables
data_4 <- read.csv(file = "./salaries_2.csv") # data scientist salaries for 2024
head(data_1, 10)
head(data_2, 5)
head(data_3, 5)
head(data_4, 5)
# checking for missing values in each dataframe
sum(is.na(data_1))
[1] 0
sum(is.na(data_2))
[1] 0
sum(is.na(data_3))
[1] 0
sum(is.na(data_4))
[1] 0
# check if there are empty strings and replace them with NA
# dplyr::mutate_all(data_1, list(~na_if(.,"")))
data_1 %>% dplyr::mutate_if(is.character, list(~na_if(.,"")))
data_2 %>% dplyr::mutate_if(is.character, list(~na_if(.,"")))